LDA models for different treatments

## Loading required package: bitops

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

All rodents

Control plots as used in original LDA paper

paper_rodent_data = read.csv('paper_dat.csv', stringsAsFactors = FALSE, colClasses = c('Date', rep('integer', 21)))
colnames(paper_rodent_data)[1] <- 'date'


paper_selected = run_rodent_LDA(rodent_data = paper_rodent_data, topics_vector = c(2, 3, 4, 5, 6),
                          nseeds = 200, ncores = 4)

plot(paper_selected)

Controls plots from portalr, for the longest time series - all rodents

control_time_rodent_data = get_rodent_lda_data(time_or_plots = 'time', treatment = 'control', type = 'rodents')


control_time_selected = run_rodent_LDA(rodent_data = control_time_rodent_data, topics_vector = c(2, 3, 4, 5, 6),
                          nseeds = 200, ncores = 4)

plot(control_time_selected)

Controls plots from portalr, for the shorter time series - all rodents

control_plots_rodent_data = get_rodent_lda_data(time_or_plots = 'plots', treatment = 'control', type = 'rodents')


control_plots_selected = run_rodent_LDA(rodent_data = control_plots_rodent_data, topics_vector = c(2, 3, 4, 5, 6),
                          nseeds = 200, ncores = 4)

plot(control_plots_selected)

Exclosure plots for the longest time series (fewer plots) - all rodents

exclosure_time_rodent_data = get_rodent_lda_data(time_or_plots = 'time', treatment = 'exclosure', type = 'rodents')


exclosure_time_selected = run_rodent_LDA(rodent_data = exclosure_time_rodent_data, topics_vector = c(2, 3, 4, 5, 6),
                          nseeds = 200, ncores = 4)

plot(exclosure_time_selected)

Exclosure plots for the shorter time series (more plots) - all rodents

exclosure_plots_rodent_data = get_rodent_lda_data(time_or_plots = 'plots', treatment = 'exclosure', type = 'rodents')


exclosure_plots_selected = run_rodent_LDA(rodent_data = exclosure_plots_rodent_data, topics_vector = c(2, 3, 4, 5, 6),
                          nseeds = 200, ncores = 4)

plot(exclosure_plots_selected)

Granviores only

Controls plots from portalr, for the longest time series - only granivores

control_time_rodent_data = get_rodent_lda_data(time_or_plots = 'time', treatment = 'control', type = 'granivores')


control_time_selected = run_rodent_LDA(rodent_data = control_time_rodent_data, topics_vector = c(2, 3, 4, 5, 6),
                          nseeds = 200, ncores = 4)

plot(control_time_selected)

Controls plots from portalr, for the shorter time series - only granivores

control_plots_rodent_data = get_rodent_lda_data(time_or_plots = 'plots', treatment = 'control', type = 'granivores')


control_plots_selected = run_rodent_LDA(rodent_data = control_plots_rodent_data, topics_vector = c(2, 3, 4, 5, 6),
                          nseeds = 200, ncores = 4)

plot(control_plots_selected)

Exclosure plots for the longest time series (fewer plots) - only granivores

exclosure_time_rodent_data = get_rodent_lda_data(time_or_plots = 'time', treatment = 'exclosure', type = 'granivores')


exclosure_time_selected = run_rodent_LDA(rodent_data = exclosure_time_rodent_data, topics_vector = c(2, 3, 4, 5, 6),
                          nseeds = 200, ncores = 4)

plot(exclosure_time_selected)

Exclosure plots for the shorter time series (more plots) - only granivores

exclosure_plots_rodent_data = get_rodent_lda_data(time_or_plots = 'plots', treatment = 'exclosure', type = 'granivores')


exclosure_plots_selected = run_rodent_LDA(rodent_data = exclosure_plots_rodent_data, topics_vector = c(2, 3, 4, 5, 6),
                          nseeds = 200, ncores = 4)

plot(exclosure_plots_selected)